© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11647
    Prev
    Next
    INDEX
    Explanations

    words related to law and months of the year, especially those starting with "J"

    oai_token-act-pair · gemini-2.0-flash

    French language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    وله
    -0.48
     насељу
    -0.48
    boutique
    -0.47
     hypotension
    -0.46
    wieś
    -0.45
    mod
    -0.44
    veling
    -0.44
     Conexion
    -0.44
    wak
    -0.43
    ouro
    -0.42
    POSITIVE LOGITS
    ')['
    0.82
    cember
    0.73
    JUST
    0.71
    '):
    0.69
     just
    0.69
     JUST
    0.69
     July
    0.68
    /**
    0.68
    ">//
    0.67
    Capítulo
    0.65
    Activations Density 0.555%

    No Known Activations